Simple Learning and Compositional Application of Perceptually Grounded Word Meanings for Incremental Reference Resolution
Simple Learning and Compositional Application of Perceptually Grounded Word Meanings for Incremental Reference Resolution
复制标题
用于增量参考分辨率的感知基础词义的简单学习和组合应用
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
David Schlangen
中科院分区：
文献类型：
--
作者：
C. Kennington;David Schlangen
使用语言的一个基本方式是指称对象。通常，这些对象物理上存在于共享环境中，并且通过提及对象的可感知属性来完成引用。这是一种语言使用类型，既不是由逻辑语义学也不是由分布语义学很好地建模，前者侧重于表达命题之间的推理关系，后者侧重于单词或短语之间的相似关系。我们提出了一个帐户的单词和短语的含义是感知接地，可训练的，成分，和“dialogueplausible”，因为它计算的意义逐字逐句。我们表明，该方法在直接描述和目标/地标描述上表现良好（在32个参考分辨率任务中的1个任务上的准确率为65%），即使在使用少于800个训练示例和自动转录的话语进行训练时也是如此。
An elementary way of using language is to refer to objects. Often, these objects are physically present in the shared environment and reference is done via mention of perceivable properties of the objects. This is a type of language use that is modelled well neither by logical semantics nor by distributional semantics, the former focusing on inferential relations between expressed propositions, the latter on similarity relations between words or phrases. We present an account of word and phrase meaning that is perceptually grounded, trainable, compositional, and ‘dialogueplausible’ in that it computes meanings word-by-word. We show that the approach performs well (with an accuracy of 65% on a 1-out-of-32 reference resolution task) on direct descriptions and target/landmark descriptions, even when trained with less than 800 training examples and automatically transcribed utterances.